2000 character limit reached
Arbitrary Time Information Modeling via Polynomial Approximation for Temporal Knowledge Graph Embedding (2405.00358v1)
Published 1 May 2024 in cs.AI and cs.LG
Abstract: Distinguished from traditional knowledge graphs (KGs), temporal knowledge graphs (TKGs) must explore and reason over temporally evolving facts adequately. However, existing TKG approaches still face two main challenges, i.e., the limited capability to model arbitrary timestamps continuously and the lack of rich inference patterns under temporal constraints. In this paper, we propose an innovative TKGE method (PTBox) via polynomial decomposition-based temporal representation and box embedding-based entity representation to tackle the above-mentioned problems. Specifically, we decompose time information by polynomials and then enhance the model's capability to represent arbitrary timestamps flexibly by incorporating the learnable temporal basis tensor. In addition, we model every entity as a hyperrectangle box and define each relation as a transformation on the head and tail entity boxes. The entity boxes can capture complex geometric structures and learn robust representations, improving the model's inductive capability for rich inference patterns. Theoretically, our PTBox can encode arbitrary time information or even unseen timestamps while capturing rich inference patterns and higher-arity relations of the knowledge base. Extensive experiments on real-world datasets demonstrate the effectiveness of our method.
- Boxe: A box embedding model for knowledge base completion. In Advances in Neural Information Processing Systems, pages 9649–9661.
- Multi-relational poincaré graph embeddings. In Advances in Neural Information Processing Systems, pages 4465–4475.
- A2N: attending to neighbors for knowledge graph inference. In Proceedings of the Conference of the Association for Computational Linguistics, pages 4387–4392.
- Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems, pages 2787–2795.
- Low-dimensional hyperbolic knowledge graph embeddings. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, pages 6901–6914.
- Rotateqvs: Representing temporal information as rotations in quaternion vector space for temporal knowledge graph completion. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, pages 5843–5857.
- Probabilistic box embeddings for uncertain knowledge graph reasoning. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 882–893.
- N.E. Cotter. 1990. The stone-weierstrass theorem and its application to neural networks. IEEE Transactions on Neural Networks, 1(4):290–295.
- Improving local identifiability in probabilistic box embeddings. In Advances in Neural Information Processing Systems, pages 182–192.
- Hyte: Hyperplane-based temporally aware knowledge graph embedding. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 2001–2011.
- Convolutional 2d knowledge graph embeddings. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 1811–1818.
- Takuma Ebisu and Ryutaro Ichise. 2018. Toruse: Knowledge graph embedding on a lie group. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 1819–1826.
- Learning sequence encoders for temporal knowledge graph completion. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 4816–4821.
- Diachronic embedding for temporal knowledge graph completion. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 3988–3995.
- Dyernie: Dynamic evolution of riemannian manifold embeddings for temporal knowledge graph completion. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 7301–7316.
- Global instance tracking: Locating target more like humans. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1):576–592.
- Encoding temporal information for time-aware link prediction. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 2350–2354.
- Seyed Mehran Kazemi and David Poole. 2018. Simple embedding for link prediction in knowledge graphs. In Advances in Neural Information Processing Systems, pages 4289–4300.
- Tensor decompositions for temporal knowledge base completion. In Proceedings of the International Conference on Learning Representations.
- Julien Leblay and Melisachew Wudage Chekol. 2018. Deriving validity time in knowledge graph. In Companion of the International World Wide Web Conferences, pages 1771–1776.
- Differentiating concepts and instances for knowledge graph embedding. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 1971–1979.
- Temporal knowledge graph completion using box embeddings. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 7779–7787.
- Quatre: Relation-aware quaternions for knowledge graph embeddings. In Companion of the International World Wide Web Conferences, pages 189–192.
- Holographic embeddings of knowledge graphs. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 1955–1961.
- A three-way model for collective learning on multi-relational data. In Proceedings of the International Conference on Machine Learning, pages 809–816.
- Allan Pinkus. 2000. Weierstrass and approximation theory. Journal of Approximation Theory, 107(1):1–66.
- Chronor: Rotation based temporal knowledge graph embedding. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 6471–6479.
- Modeling relational data with graph convolutional networks. In Proceedings of the European Semantic Web Conference, volume 10843, pages 593–607.
- Rotate: Knowledge graph embedding by relational rotation in complex space. In Proceedings of the International Conference on Learning Representations.
- Complex embeddings for simple link prediction. In Proceedings of the International Conference on Machine Learning, volume 48, pages 2071–2080.
- Probabilistic embedding of knowledge graphs with box lattice measures. In Proceedings of the Annual Meeting of the Association for Computational Linguistics, pages 263–272.
- Chun-Chih Wang and Pu-Jen Cheng. 2018. Translating representations of knowledge graphs with neighbors. In Proceedings of the International ACM SIGIR Conference on Research & Development in Information Retrieval, pages 917–920.
- Mixed-curvature multi-relational graph neural network for knowledge graph completion. In Proceedings of the International World Wide Web Conference, pages 1761–1771.
- Knowledge graph embedding by translating on hyperplanes. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 1112–1119.
- Tero: A time-aware knowledge graph embedding via temporal rotation. In Proceedings of the International Conference on Computational Linguistics, pages 1583–1593.
- Temporal knowledge graph completion based on time series gaussian embedding. In Proceedings of the International Semantic Web Conference, pages 654–671.
- Embedding entities and relations for learning and inference in knowledge bases. In Proceedings of the International Conference on Learning Representations.
- Quaternion knowledge graph embeddings. In Advances in Neural Information Processing Systems, pages 2731–2741.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.